检索结果-南通市图书馆

Knowledge Extraction Model for power Load Characteristics of Special Days and Extreme Weather

2011 IEEE International Conference on computer Science and Automation engineering(CSAE 2011)

作者： shi-jiao ZHU School of computer and information engineering shanghai university of electric power shanghai 200090 China Jun YANG School of computer and information engineering shanghai university of electric power shanghai 200090 China

neural networks are widely used in different ***,fixed architecture is difficult to use in practice for its pre-determined neurons and *** architecture is proposed in this paper for neural network based on idea of human’s cognition where each neuron has its own priority number and evolution of learning process with *** prediction theory,risk bound of the architecture with multi-weighted neurons are *** results show that the propose method outperforms the SVM method using limited *** proposed method is constructive and this work can provide a very useful method for neural network learning model.

关键词： Neural Network Risk bound MultiWeighted

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Knowledge Extraction Model for Power Load Characteristics of...

基于RF和自注意力ResNet的变压器PDPR

2009 IEEE International Conference on Intelligent Computing and Intelligent Systems(ICIS2009)

作者： Dou Quansheng School of computer Science and Technology,Shandong Institute of Business and Technology,Yantai,China shi Zhongzhi Institute of Computing Technology,Chinese Academy of Sciences,Beijing,China Pan Guanyu Department of information engineering,JiLin Business and Technology College,Changchun,China Yang Bin Heilongjing electric power Company Limited Harbin,China

Load forecasting is a traditional research field of power system,under normal circumstance,there are great similarities between the similar days,but under the condition of special days and extreme weather,load prediction has some *** model for load characteristics of special days and extreme weather was proposed in this paper,coding strategy and genetic operation of traditional genetic algorithm were redefined in the model,the relational rules about relation between power load special days and extreme weather were *** the same time,the credibility of these rules was proven by practice.

关键词： load forecasting rules extraction

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

计算机仿真 2024年第6期41卷 146-151页

作者：蒋伟石欣月上海电力大学电子与信息工程学院上海200000

变压器局放是影响电网高效稳定运行的重要因素,也是变压器状态检测的重要内容。准确检测局放和识别局放类型是及时发现故障、排除隐患的前提。针对现有识别方法存在准确率不高的问题,提出一种基于RF和自注意力残差网络的变压器局放模式... 详细信息

变压器局放是影响电网高效稳定运行的重要因素,也是变压器状态检测的重要内容。准确检测局放和识别局放类型是及时发现故障、排除隐患的前提。针对现有识别方法存在准确率不高的问题,提出一种基于RF和自注意力残差网络的变压器局放模式识别方法。方法构建了基于RF和自注意力残差模型,针对残差网络分类性能较低的问题,引入随机森林RF作为分类器,提高识别率的同时避免网络退化;并在特征提取器中融入自注意力机制,优化局放特征,加快模型训练。实验结果表明,所提方法可以较为准确地识别变压器局放的模式,准确率达98.96%,通过交叉实验验证,实际场景下,能够对不同环境下多种电压等级的变压器局放模式有效识别,具有较好的通用性。

关键词：变压器局放模式识别残差网络随机森林自注意力机制

融合注意力机制的MSCNN-BiLSTM滚动轴承故障诊断方法

在线全文

学校读者我要写书评

暂无评论

轴承 2024年第8期 86-94页

作者：谢扬筱王国强石念峰杨向兰王勇上海电力大学计算机科学与技术学院上海201306 洛阳理工学院计算机与信息工程学院河南洛阳471023 河南科技大学信息工程学院河南洛阳471023

针对传统故障诊断方法故障特征提取能力不足导致在变载荷和噪声干扰场景下诊断效果不佳的问题,提出了一种融合注意力机制的多尺度卷积神经网络(MSCNN)和双向长短时记忆网络(BiLSTM)结合的滚动轴承故障诊断方法。利用通道注意力机制优化... 详细信息

针对传统故障诊断方法故障特征提取能力不足导致在变载荷和噪声干扰场景下诊断效果不佳的问题,提出了一种融合注意力机制的多尺度卷积神经网络(MSCNN)和双向长短时记忆网络(BiLSTM)结合的滚动轴承故障诊断方法。利用通道注意力机制优化卷积神经网络(CNN)学习机制,构建多尺度特征提取模块自适应提取不同尺度的关键空间特征信息,利用BiLSTM对时间序列的学习能力提取振动信号的时序特征信息,引入自注意力机制关注重要故障特征,最后使用Softmax分类器进行轴承故障诊断。试验结果表明,该模型能充分提取原始振动信号的故障特征,与其他故障诊断模型相比,其诊断精度高,泛化性强,能够在变载荷和噪声干扰的情况下保持较高的诊断准确率。

关键词：滚动轴承故障诊断特征提取卷积神经网络注意力机制

Large circuit models: opportunities and challenges

同方期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第10期67卷 25-66页

作者： Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan shi Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y.YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU Huawei Noah’s Ark Lab School of Integrated Circuits Peking University faculty of electrical engineering and computer Science Ningbo University Department of Electronic and computer engineering Hong Kong University of Science and Technology Department of computer Science and engineering The Chinese University of Hong Kong School of Integrated Circuits Southeast University Huawei HiSilicon Peng Cheng Laboratory School of computer Science Peking University School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University School of Artificial Intelligence Shanghai Jiao Tong University

Within the electronic design automation(EDA) domain, artificial intelligence(AI)-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an “AI4EDA” approach falls short of achieving a holistic design synthesis and understanding,overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This study argues for a paradigm shift from AI4EDA towards AI-rooted EDA from the ground up, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, register-transfer level(RTL) designs, circuit netlists,and physical layouts. We champion the creation of large circuit models(LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-rooted philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound “shift-left” in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design-tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area(PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.

关键词： AI-rooted EDA large circuit models (LCMs) multimodal circuit representation learning circuit optimization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

面向工业物联网时序数据的异常检测方法

计算机工程与应用 2024年第12期60卷 270-282页

作者：谢伟卢士达时宽治王虹岚顾荣斌黄君李静国网上海市电力公司上海200122 国网上海市电力公司信息通信公司上海200072 南京航空航天大学计算机科学与技术学院南京211106

作为第四次工业革命重要基石,工业互联网将孤立的工业系统转化为连接的网络,是数字产业化的重要拓展方向,工业物联网环境中的异常检测对自动化决策具有重要意义。针对现有大多数方法未能有效地考虑传感器间复杂的未知拓扑关系以及工业... 详细信息

作为第四次工业革命重要基石,工业互联网将孤立的工业系统转化为连接的网络,是数字产业化的重要拓展方向,工业物联网环境中的异常检测对自动化决策具有重要意义。针对现有大多数方法未能有效地考虑传感器间复杂的未知拓扑关系以及工业物联网时序数据内在的不同尺度模式导致异常检测精度有待提升的问题,提出了一种面向工业物联网时序数据的多尺度时空特征融合无监督异常检测方法MSTSAD,构建了一种新颖的双向时空特征提取模块依次捕获多个时间序列之间的相关性和双向依赖性。设计了多尺度门控时间卷积神经网络自适应地提取时间序列的多尺度时序特征,并引入双仿射实现多尺度时序特征和时空特征的交叉融合,增强模型对原始数据的特征提取。提出了结合对抗训练的变分自编码器来放大异常的重构误差并增强模型对训练数据噪声的抗干扰能力,提高了模型对异常数据的区分能力。在GPW、ECG5000、Occupancy和SWaT四个公开数据集上与五种先进方法进行了对比实验,实验结果表明,MSTSAD的F1分数提升了0.015~0.047。

关键词：工业物联网异常检测多尺度时空信息

基于MTF可视化和改进DenseNet神经网络的电能质量扰动识别算法

在线全文

学校读者我要写书评

暂无评论

电力科学与技术学报 2024年第4期39卷 102-111页

作者：时帅陈子文黄冬梅贺琪孙园胡伟上海电力大学电气工程学院上海200090 上海电力大学计算机与技术学院上海200090 上海海洋大学信息学院上海201306 上海电力大学数理学院上海200090 上海电力大学经济与管理学院上海200090

针对传统电能质量扰动(power quality disturbances,PQDs)分类器人工选取特征过程复杂、精细化程度不足的问题,提出一种基于马尔科夫迁移场(Markov translate filed,MTF)可视化和改进密集卷积网络(dense convolu-tional networks,DenseNet)的PQDs识别新方法。首先将一维PQD信号经MTF映射为二维图像,接着将图像输入到具有新型通道注意力机制的改进DenseNet中,最后训练网络自行从海量样本中提取特征,实现PQDs信号的正确识别。算例结果表明:在无噪声和信噪比为20、30 dB情况下,所提改进DenseNet能有效克服传统方法中主观性强、抗噪性能差等特征缺点,可以更好地提取复合PQD特征信息,对复合PQD识别率高。

关键词：电能质量扰动马尔科夫迁移场可视化密集卷积网络通道注意力机制分类识别

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

基于图神经网络的多源异构知识增强对话模型

科学技术与工程 2024年第17期24卷 7196-7204页

作者：毕忠勤张锴单美静王世洋曾振柄上海电力大学计算机科学与技术学院上海200090 华东政法大学信息科学与技术系上海201620 上海大学数学系上海200444

为解决当前开放域对话系统中端到端模型在生成响应时存在的相关性低、多样性不足的问题,提出了一种多源异构知识增强对话生成模型(multi-source knowledge-enhanced dialogue generation framework,MSGF)。该模型通过整合多个不同的知识... 详细信息

为解决当前开放域对话系统中端到端模型在生成响应时存在的相关性低、多样性不足的问题,提出了一种多源异构知识增强对话生成模型(multi-source knowledge-enhanced dialogue generation framework,MSGF)。该模型通过整合多个不同的知识源,提高了与对话背景信息相关的知识覆盖率,并采用全局知识选择模块解决不同知识源之间的主题冲突问题,来避免对话主题含义混淆。此外,该模型还引入了融合预测模块,通过获取不同的知识源中的信息来生成响应。实验结果表明,与同类其他模型相比,MSGF模型在性能上具有明显优势,具有更全面的知识覆盖,生成的响应主题相关性更高。可见,所提出的MSGF模型能够很好地理解对话内容,并显著提升对话系统的性能。

关键词：对话生成图神经网络图注意力机制知识图谱多源异构知识知识增强

Decentralized Multigrid for In-situ Big Data Computing

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2015年第6期20卷 545-559页

作者： Goutham Kamath Lei shi Edmond Chow Wenzhan Song Junjie Yang Department of computer Science Georgia State University College of Computing Georgia Institute of Technology School of electric and information engineering Shanghai University of Electric Power

Modern seismic sensors are capable of recording high precision vibration data continuously for several months. Seismic raw data consists of information regarding earthquake’s origin time, location, wave velocity, ***, these high volume data are gathered manually from each station for analysis. This process restricts us from obtaining high-resolution images in real-time. A new in-network distributed method is required that can obtain a high-resolution seismic tomography in real time. In this paper, we present a distributed multigrid solution to reconstruct seismic image over large dense networks. The algorithm performs in-network computation on large seismic samples and avoids expensive data collection and centralized computation. Our evaluation using synthetic data shows that the proposed method accelerates the convergence and reduces the number of messages exchanged. The distributed scheme balances the computation load and is also tolerant to severe packet loss.

关键词： distributed multigrid cyber physical system big da